Cloud classification: principles and applications

Abstract

Clouds classification is essentially required in weather forecasting and climate related study. Detection, removal and classification of cloud are the major challenges to deal with in satellite-based images. In this paper, literature survey on cloud classification techniques published during 2000 to 2018 is presented. In recent years, various approaches are applied for cloud classification such as threshold-based, machine learning, clustering, K-means, k-nearest-neighbour (K-NN) algorithm and hybrid approach. Threshold-based is the easiest approach but it fails to classify cloud in complex sky conditions. It is also unable to classify cloud at night time. Machine learning-based approach gives highest accuracy but it depends on various parameters like day/night time, weather season, types of satellite and geographical region of the cloud. It is recommended to have hybrid model with the use of machine learning, threshold values and physical parameters.